Guaranteed characterization of exact non-asymptotic confidence regions as defined by LSCR and SPS

Abstract : In parameter estimation, it is often desirable to supplement the estimates with an assessment of their quality. A new family of methods proposed by Campi et al. for this purpose is particularly attractive, as it makes it possible to obtain exact, non-asymptotic confidence regions under mild assumptions on the noise distribution. A bottleneck of this approach, however, is the numerical characterization of these confidence regions. So far, it has been carried out by gridding, which provides no guarantee as to its results and is only applicable to low dimensional spaces. This paper shows how interval analysis can contribute to removing this bottleneck.
Complete list of metadatas

https://hal-supelec.archives-ouvertes.fr/hal-00935817
Contributor : Michel Kieffer <>
Submitted on : Friday, January 24, 2014 - 10:45:33 AM
Last modification on : Wednesday, July 3, 2019 - 3:02:02 PM
Long-term archiving on : Thursday, April 24, 2014 - 10:17:24 PM

Files

Automatica_Final.pdf
Files produced by the author(s)

Identifiers

Citation

Michel Kieffer, Eric Walter. Guaranteed characterization of exact non-asymptotic confidence regions as defined by LSCR and SPS. Automatica, Elsevier, 2014, 50 (2), pp.507-512. ⟨10.1016/j.automatica.2013.11.010⟩. ⟨hal-00935817⟩

Share

Metrics

Record views

545

Files downloads

321